Saved in:
Bibliographic Details
Main Authors: Hu, Juan, Fan, Shaojing, Sim, Terence
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.14807
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916852401176576
author Hu, Juan
Fan, Shaojing
Sim, Terence
author_facet Hu, Juan
Fan, Shaojing
Sim, Terence
contents Multi-face deepfake videos are becoming increasingly prevalent, often appearing in natural social settings that challenge existing detection methods. Most current approaches excel at single-face detection but struggle in multi-face scenarios, due to a lack of awareness of crucial contextual cues. In this work, we develop a novel approach that leverages human cognition to analyze and defend against multi-face deepfake videos. Through a series of human studies, we systematically examine how people detect deepfake faces in social settings. Our quantitative analysis reveals four key cues humans rely on: scene-motion coherence, inter-face appearance compatibility, interpersonal gaze alignment, and face-body consistency. Guided by these insights, we introduce \textsf{HICOM}, a novel framework designed to detect every fake face in multi-face scenarios. Extensive experiments on benchmark datasets show that \textsf{HICOM} improves average accuracy by 3.3\% in in-dataset detection and 2.8\% under real-world perturbations. Moreover, it outperforms existing methods by 5.8\% on unseen datasets, demonstrating the generalization of human-inspired cues. \textsf{HICOM} further enhances interpretability by incorporating an LLM to provide human-readable explanations, making detection results more transparent and convincing. Our work sheds light on involving human factors to enhance defense against deepfakes.
format Preprint
id arxiv_https___arxiv_org_abs_2507_14807
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Seeing Through Deepfakes: A Human-Inspired Framework for Multi-Face Detection
Hu, Juan
Fan, Shaojing
Sim, Terence
Computer Vision and Pattern Recognition
Artificial Intelligence
Multi-face deepfake videos are becoming increasingly prevalent, often appearing in natural social settings that challenge existing detection methods. Most current approaches excel at single-face detection but struggle in multi-face scenarios, due to a lack of awareness of crucial contextual cues. In this work, we develop a novel approach that leverages human cognition to analyze and defend against multi-face deepfake videos. Through a series of human studies, we systematically examine how people detect deepfake faces in social settings. Our quantitative analysis reveals four key cues humans rely on: scene-motion coherence, inter-face appearance compatibility, interpersonal gaze alignment, and face-body consistency. Guided by these insights, we introduce \textsf{HICOM}, a novel framework designed to detect every fake face in multi-face scenarios. Extensive experiments on benchmark datasets show that \textsf{HICOM} improves average accuracy by 3.3\% in in-dataset detection and 2.8\% under real-world perturbations. Moreover, it outperforms existing methods by 5.8\% on unseen datasets, demonstrating the generalization of human-inspired cues. \textsf{HICOM} further enhances interpretability by incorporating an LLM to provide human-readable explanations, making detection results more transparent and convincing. Our work sheds light on involving human factors to enhance defense against deepfakes.
title Seeing Through Deepfakes: A Human-Inspired Framework for Multi-Face Detection
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2507.14807